The OCR approach is rephrased as Segmentation Transformer: https://arxiv.org/abs/1909.11065. This is an official implementation of semantic segmentation for HRNet. https://arxiv.org/abs/1908.07919
transformer
segmentation
high-resolution
semantic-segmentation
cityscapes
pascal-context
lip
high-resolution-net
hrnets
segmentation-transformer
-
Updated
Jul 20, 2021 - Python
Hi,
I tried to follow README instructions for training on my own dataset but it didn't work. Here is what I did:
DATA_DIRto point to dataset dirDATA_LIST_PATH to point to train dataset list file.INPUT_SIZEto'1280, 720'NUM_CLASSESto 1LAMBDA1andLAMBDA2to0.4and0.6respectively.Then ran cmd